Can the RTX Spark N1X (128 GB) run Llama 3.1 8B?
Yes. Llama 3.1 8B fits the RTX Spark N1X (128 GB)'s 128 GB at Q4_K_M (about 7.3 GB needed), running at an estimated 29 tok/s. There's room for up to FP16 if you want higher quality.
Every quantization
Llama 3.1 8B (8B) on 128 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 5.5 GB | 7.3 GB | Fits easily | ~29 tok/s |
| Q5_K_M | 7 GB | 8.8 GB | Fits easily | ~22 tok/s |
| Q8_0 | 10 GB | 11.8 GB | Fits easily | ~16 tok/s |
| FP16 | 16 GB | 17.8 GB | Fits easily | ~9.8 tok/s |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the RTX Spark N1X (128 GB)'s 273 GB/s bandwidth (Estimated from memory bandwidth (llama.cpp decode); bandwidth assumed equal to DGX Spark (GB10), which shares the 6,144-core GPU - NVIDIA has not published an N1X figure). Long contexts need more memory and run slower.
Run it
Copy, paste, go
ollama run llama3.1:8bllama-server -hf bartowski/Meta-Llama-3.1-8B-Instruct-GGUF -ngl 99Ollama pulls a Q4 build by default. Pick a larger quant only if the table above says it fits. Full Llama 3.1 8B details →
Compare
Same model, other hardware - and other models on this card
Llama 3.1 8B on other hardware
- RTX 5090~187 tok/s
- RTX 5090 D~187 tok/s
- RTX 6000D~164 tok/s
- RTX 4090~114 tok/s
- RTX 3090~100 tok/s
- Radeon RX 7900 XTX~100 tok/s
- RTX 5080~100 tok/s
- RTX 3080 Ti~95 tok/s
Also runs on the RTX Spark N1X (128 GB)
- gpt-oss-120b~35 tok/s
- Qwen2.5 72B~3.9 tok/s
- Llama 3.3 70B~3.9 tok/s
- Qwen3.6 35B A3B~60 tok/s
- Qwen3.5 35B A3B~60 tok/s
- dolphin-2.9.1-yi-1.5-34b~7.8 tok/s
- Gemma 4 31B~8.3 tok/s
- Qwen3 32B~8.3 tok/s
Frequently asked
Quick answers
Can the NVIDIA RTX Spark N1X (128 GB) run Llama 3.1 8B?
Yes. Llama 3.1 8B fits the RTX Spark N1X (128 GB)'s 128 GB at Q4_K_M (about 7.3 GB needed), running at an estimated 29 tok/s. There's room for up to FP16 if you want higher quality.
How much VRAM does Llama 3.1 8B need?
About 5.5 GB of weights at Q4_K_M, 10 GB at Q8_0 and 16 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Llama 3.1 8B on the RTX Spark N1X (128 GB)?
Roughly 29 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the RTX Spark N1X (128 GB)'s 273 GB/s memory bandwidth.